INDEX

Explanations

references to the philosopher Karl Marx and his related terms

oai_token-act-pair · gpt-3.5-turbo

references to Karl Marx and related concepts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 captcha

-0.82

ittee

-0.72

cue

-0.68

cffff

-0.66

 Ukrain

-0.64

 cavity

-0.64

 slot

-0.63

velength

-0.62

conservancy

-0.62

 Immunity

-0.62

POSITIVE LOGITS

geist

1.13

 Marx

1.02

Marx

1.02

Lenin

0.95

 Engels

0.90

enstein

0.90

enthal

0.85

sson

0.81

ian

0.78

ists

0.77

Activations Density 0.008%

references to the philosopher Karl Marx and his related terms

references to Karl Marx and related concepts

No Comments

No Known Activations